Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models

• URL: http://arxiv.org/abs/2608.11657v2
• Date: Mon, 17 Aug 2026 13:54:51 GMT
• Title: Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models
• Abstract summary: We introduce Semantic Lenia, an artificial life framework that transforms Large Language Model (LLM) inference into a continuous, closed-loop dynamical system.<n>We demonstrate the emergence of Homeostatic Solitons''-metastable semantic structures that actively resist repetitive crystallization.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce Semantic Lenia, an artificial life framework that transforms Large Language Model (LLM) inference from a static optimization problem into a continuous, closed-loop dynamical system. By establishing a non-linear homeostatic feedback loop to dynamically balance semantic attraction and syntactic repulsion, we demonstrate the emergence of ``Homeostatic Solitons''-metastable semantic structures that actively resist repetitive crystallization. Our exhaustive parameter sweeps map a critical ``Habitable Ridge'' where applied steering forces balance the model's intrinsic syntactic inertia. This approach successfully maintains generative trajectories in a numerically sensitive critical regime, triggering profound abductive leaps without structural collapse, and reveals a capacity-dependent scaling trend in the syntactic inertia across different model sizes.

Related papers

• Fluctuation-Induced Bistability in the Dissipative Dynamics of Generic Cavity-Matter Quantum Systems [0.0]
  We identify a common microscopic mechanism based on resonances between photonic transitions and many-body energy scales.<n>We develop complementary methods to study both the steady-state properties of fluctuation-induced bistability and its dynamical formation at finite times.<n>Our results establish fluctuation-induced bistability as a universal feature of dissipative cavity-coupled many-body systems.
  arXiv  Detail & Related papers  (2026-07-23T13:21:19Z)
• CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts [5.265601895449634]
  CaLiSym is a lightweight framework that extends symplectic learning to such systems by changing where the geometric prior is imposed.<n>We instantiate the framework with SympNet predictors and introduce GRB-SympNet, a B-spline variant combining approximation with exact symplectic structure.<n>The lifted dynamics preserve the symplectic form to numerical precision, extending symplectic learning beyond conservative mechanics toward real-world robotics.
  arXiv  Detail & Related papers  (2026-07-07T21:41:59Z)
• Decoupling band topology from criticality in bosonic systems [0.0]
  A new understanding of criticality in systems described by quadratic bosonic Hamiltonians (QBHs) ties the emergence of long-range correlations to boundaries of dynamical stability.<n>We investigate the interplay of this landscape of possibilities with band topology and boundary physics.
  arXiv  Detail & Related papers  (2026-07-01T18:00:08Z)
• Learning Spatio-Temporal Foundation Models from Pure Synthetic Data [85.23980441738811]
  NeoST is a scalable synthetic-training corpus to real-world bias, a latent-space reasoning architecture that generates and iteratively refines multiple future trajectories, and latent-space objectives that emphasize structural dynamics and enable inference-time correction under distribution shifts.<n>Extensive experiments across diverse real-world benchmarks show that NeoST consistently outperforms existing STFMs in diverse real-worldtemporal systems.
  arXiv  Detail & Related papers  (2026-06-27T02:56:46Z)
• Dimension-Free Saddle-Point Escape in Muon [10.480246288279517]
  Modern Large Language Model (LLM) training is bottlenecked by pathologically flat saddle points in extreme high-dimensional landscapes.<n>Motivated by this challenge, we analyze the saddle-point escape dynamics of the emerging Muon.
  arXiv  Detail & Related papers  (2026-05-10T05:06:07Z)
• Structural Instability of Feature Composition [2.5754366051855837]
  We study the compositional-collapse threshold under a spherical dictionary model.<n>We show that, in the high-bias regime, ReLU converts microscopic correlation-induced variance fluctuations into a systematic drift.<n>We validate the predicted scaling trends on structured semantic features extracted from CLEVR.
  arXiv  Detail & Related papers  (2026-04-18T05:53:31Z)
• Gravitationally induced wave-function collapse from dynamical bifurcation [0.0]
  We show that wave-function collapse emerges as a deterministic dynamical instability induced by gravitational self-interaction and regulated by short-distance repulsion.<n>The mechanism provides a controlled and quantitative realization of gravity-induced pathological localization, extending Schrdinger--Newton-type models.
  arXiv  Detail & Related papers  (2026-04-17T15:15:38Z)
• MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation [60.48914865049489]
  MotionCFG is a framework that enhances motion dynamics by contrasting a target concept with its noise-blured counterparts.<n>Unlike explicit negations, this approach facilitates implicit hard negative guidance without shifting the global semantic identity.<n> MotionCFG consistently improves motion dynamics across state-of-the-art T2V frameworks.
  arXiv  Detail & Related papers  (2026-03-14T18:39:37Z)
• Emergent Manifold Separability during Reasoning in Large Language Models [46.78826734548872]
  Chain-of-Thought prompting significantly improves reasoning in Large Language Models.<n>We quantify the linear separability of latent representations without the confounding factors of probe training.
  arXiv  Detail & Related papers  (2026-02-23T20:36:17Z)
• KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra [65.11254608352982]
  We introduce a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators.<n>By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation.
  arXiv  Detail & Related papers  (2026-02-15T06:32:23Z)
• Dynamical metastability and transient topological magnons in interacting driven-dissipative magnetic systems [0.0]
  We extend dynamical metastability into the nonlinear, interacting regime and identify magnetic heterostructures as a natural platform for its exploration.<n>Our results constitute the first systematic study of dynamical metastability in nonlinear dynamics.
  arXiv  Detail & Related papers  (2026-02-13T19:00:04Z)
• Aligning Agentic World Models via Knowledgeable Experience Learning [68.85843641222186]
  We introduce WorldMind, a framework that constructs a symbolic World Knowledge Repository by synthesizing environmental feedback.<n>WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
  arXiv  Detail & Related papers  (2026-01-19T17:33:31Z)
• Generative System Dynamics in Recurrent Neural Networks [56.958984970518564]
  We investigate the continuous time dynamics of Recurrent Neural Networks (RNNs)<n>We show that skew-symmetric weight matrices are fundamental to enable stable limit cycles in both linear and nonlinear configurations.<n> Numerical simulations showcase how nonlinear activation functions not only maintain limit cycles, but also enhance the numerical stability of the system integration process.
  arXiv  Detail & Related papers  (2025-04-16T10:39:43Z)
• Decimation technique for open quantum systems: a case study with driven-dissipative bosonic chains [62.997667081978825]
  Unavoidable coupling of quantum systems to external degrees of freedom leads to dissipative (non-unitary) dynamics. We introduce a method to deal with these systems based on the calculation of (dissipative) lattice Green's function. We illustrate the power of this method with several examples of driven-dissipative bosonic chains of increasing complexity.
  arXiv  Detail & Related papers  (2022-02-15T19:00:09Z)
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems [74.80320120264459]
  We present an approach to learn such motions from a limited number of human demonstrations. The complex motions are encoded as rollouts of a stable dynamical system. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.
  arXiv  Detail & Related papers  (2020-05-27T03:51:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.